SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Fix typo in Greedy Search Description (#22345)

Browse Source 
Fix typo in greedy search docs
This commit is contained in:
Ashwin Mathur
2023-03-24 17:02:18 +05:30
committed by GitHub
parent c0fa2aa0b8
commit b79607656b
1 changed files with 1 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/source/en/generation_strategies.mdx
View File

@@ -149,7 +149,6 @@ Here, we'll show some of the parameters that control the decoding strategies and
### Greedy Search ### Greedy Search
[`generate`] uses greedy search decoding by default so you don't have to pass any parameters to enable it. This means the parameters `num_beams` is set to 1 and `do_sample=False`. [`generate`] uses greedy search decoding by default so you don't have to pass any parameters to enable it. This means the parameters `num_beams` is set to 1 and `do_sample=False`.
`do_sample=False`. Because it is a default strategy, you do not have to pass any parameters to `generate()` method to enable it.
```python ```python
>>> from transformers import AutoModelForCausalLM, AutoTokenizer >>> from transformers import AutoModelForCausalLM, AutoTokenizer